Agents & Tool Calling
ZICQ LLM rankings update daily across intelligence, coding, price, and context for selection and comparison.
Last updated: 10 min ago (2026-11-18 11:41)Sources and methodology
Ranked by OpenRouter benchmarks.agentic_index (agent / tool-calling index) plus the supported_parameters.tools flag — a reference for agent framework builders.
2. Benchmarks:Intelligence, coding, and agentic indices are sourced directly from Artificial Analysis (artificialanalysis.ai) official benchmark indices.
3. Overall Score Weights:Overall Score = 60% × Intelligence Index + 25% × Coding Index + 15% × Agentic Index. Models without benchmark data are ranked at the end.
4. Referral links:"Try it" buttons marked "Referral" are referral links; ZICQ may earn a commission. Referral relationships never affect rankings or scores.
Statistics for this selection
⚡ Side-by-Side Model PK & Token Cost Calculator Click "+ Compare" on any model below to swap · Live monthly cost calculator · Shareable comparison URL
| Metric | DeepSeek: DeepSeek V4 Flash Vision Exp DeepSeek | DeepSeek: DeepSeek V4 Pro 0813 DeepSeek | DeepSeek: DeepSeek V4 Flash 0731 DeepSeek |
|---|---|---|---|
| Intelligence / Coding / Agentic | 0.0 / 65.0 / 47.5 | 23.1 / 68.8 / 41.3 | 0.0 / 69.1 / 41.0 |
| Context Window | 1.0M tokens | 1.0M tokens | 1.0M tokens |
| Input / Output Price (1M) | $0.44 / $1.32 | $0.11 / $4.44 | $0.06 / $0.18 |
| Est. Monthly Cost (30d) | Adjust inputs to calculate | Adjust inputs to calculate | Adjust inputs to calculate |
-
#20
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
Tools Vision Reasoning StructuredIntelligence 0.0Agentic 47.5Context 1.0M Output ≤ 943K$0.44/1M $1.32/1M out cache $0.01/1MSolid Tool Calling -
#34
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Tools Reasoning StructuredIntelligence 23.1Agentic 41.3Context 1.0M Output ≤ 943K$0.11/1M $4.44/1M out cache $0.10/1MSolid Tool Calling -
#36
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Tools Reasoning StructuredIntelligence 0.0Agentic 41.0Context 1.0M Output ≤ 384K$0.06/1M $0.18/1M out cache $0.01/1MSolid Tool Calling -
#37
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Tools Reasoning StructuredIntelligence 0.0Agentic 41.0Context 1.0M Output ≤ 384K$0.05/1M $0.14/1M out cache $0.01/1MSolid Tool Calling -
#68
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Tools Reasoning StructuredIntelligence 0.0Agentic 22.2Context 1.0M Output ≤ 393K$0.09/1M $0.18/1M out cache $0.02/1MSolid Tool Calling -
#102
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
Tools Reasoning StructuredIntelligence 0.0Agentic 6.8Context 163K Output ≤ 147K$0.27/1M $1.00/1M outSolid Tool Calling -
#134
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
Tools StructuredIntelligence 0.0Agentic 0.8Context 163K Output ≤ 115K$0.29/1M $1.14/1M out cache $0.11/1MSolid Tool Calling -
#172
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
Tools Vision Reasoning StructuredIntelligence 32.6Agentic 0.0Context 1.0M Output ≤ 943K$0.04/1M $0.50/1M out cache $0.01/1MSolid Tool Calling -
#173
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
Tools Vision Reasoning StructuredIntelligence 32.6Agentic 0.0Context 1.0M Output ≤ 943K$0.04/1M $0.15/1M out cache $0.00/1MSolid Tool Calling -
#185
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
Tools Reasoning StructuredIntelligence 20.8Agentic 0.0Context 1.0M Output ≤ 393K$0.90/1M $1.50/1M out cache $0.25/1MSolid Tool Calling -
#249
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Tools Vision Reasoning StructuredContext 1.0M Output ≤ 943K$0.05/1M $0.57/1M out cache $0.02/1MSolid Tool Calling -
#250
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Tools Vision Reasoning StructuredContext 1.0M Output ≤ 131K$0.11/1M $0.34/1M out cache $0.00/1MSolid Tool Calling -
#347
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Tools Reasoning StructuredIntelligence 0.0Agentic 0.0Context 163K Output ≤ 147K$0.26/1M $0.38/1M out cache $0.13/1MSolid Tool Calling -
#368
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Tools Reasoning StructuredContext 163K Output ≤ 147K$0.27/1M $0.41/1M outSolid Tool Calling -
#376
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Tools Reasoning StructuredContext 163K Output ≤ 147K$0.25/1M $0.95/1M out cache $0.13/1MSolid Tool Calling -
#403
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
Tools Reasoning StructuredContext 163K Output ≤ 32K$0.50/1M $2.15/1M out cache $0.35/1MSolid Tool Calling -
#432
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Tools StructuredContext 163K Output ≤ 16K$0.26/1M $1.03/1M outSolid Tool Calling